Fifa analysis¶

In [1]:
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import seaborn as sns
sns.set(style="whitegrid")
import matplotlib.pyplot as plt
from collections import Counter
%matplotlib inline

# Input data files are available in the "../input/" directory.
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# Any results you write to the current directory are saved as output.
In [2]:
# ignore warnings
import warnings
warnings.filterwarnings('ignore')
In [5]:
fifa19 = pd.read_csv(r'C:\Users\Jithender\Music\11th_resume project\Seaborn\FIFA.csv', index_col=0)
In [6]:
fifa19.head()
Out[6]:
ID Name Age Photo Nationality Flag Overall Potential Club Club Logo ... Composure Marking StandingTackle SlidingTackle GKDiving GKHandling GKKicking GKPositioning GKReflexes Release Clause
0 158023 L. Messi 31 https://cdn.sofifa.org/players/4/19/158023.png Argentina https://cdn.sofifa.org/flags/52.png 94 94 FC Barcelona https://cdn.sofifa.org/teams/2/light/241.png ... 96.0 33.0 28.0 26.0 6.0 11.0 15.0 14.0 8.0 €226.5M
1 20801 Cristiano Ronaldo 33 https://cdn.sofifa.org/players/4/19/20801.png Portugal https://cdn.sofifa.org/flags/38.png 94 94 Juventus https://cdn.sofifa.org/teams/2/light/45.png ... 95.0 28.0 31.0 23.0 7.0 11.0 15.0 14.0 11.0 €127.1M
2 190871 Neymar Jr 26 https://cdn.sofifa.org/players/4/19/190871.png Brazil https://cdn.sofifa.org/flags/54.png 92 93 Paris Saint-Germain https://cdn.sofifa.org/teams/2/light/73.png ... 94.0 27.0 24.0 33.0 9.0 9.0 15.0 15.0 11.0 €228.1M
3 193080 De Gea 27 https://cdn.sofifa.org/players/4/19/193080.png Spain https://cdn.sofifa.org/flags/45.png 91 93 Manchester United https://cdn.sofifa.org/teams/2/light/11.png ... 68.0 15.0 21.0 13.0 90.0 85.0 87.0 88.0 94.0 €138.6M
4 192985 K. De Bruyne 27 https://cdn.sofifa.org/players/4/19/192985.png Belgium https://cdn.sofifa.org/flags/7.png 91 92 Manchester City https://cdn.sofifa.org/teams/2/light/10.png ... 88.0 68.0 58.0 51.0 15.0 13.0 5.0 10.0 13.0 €196.4M

5 rows × 88 columns

In [7]:
fifa19.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 18207 entries, 0 to 18206
Data columns (total 88 columns):
 #   Column                    Non-Null Count  Dtype  
---  ------                    --------------  -----  
 0   ID                        18207 non-null  int64  
 1   Name                      18207 non-null  object 
 2   Age                       18207 non-null  int64  
 3   Photo                     18207 non-null  object 
 4   Nationality               18207 non-null  object 
 5   Flag                      18207 non-null  object 
 6   Overall                   18207 non-null  int64  
 7   Potential                 18207 non-null  int64  
 8   Club                      17966 non-null  object 
 9   Club Logo                 18207 non-null  object 
 10  Value                     18207 non-null  object 
 11  Wage                      18207 non-null  object 
 12  Special                   18207 non-null  int64  
 13  Preferred Foot            18159 non-null  object 
 14  International Reputation  18159 non-null  float64
 15  Weak Foot                 18159 non-null  float64
 16  Skill Moves               18159 non-null  float64
 17  Work Rate                 18159 non-null  object 
 18  Body Type                 18159 non-null  object 
 19  Real Face                 18159 non-null  object 
 20  Position                  18147 non-null  object 
 21  Jersey Number             18147 non-null  float64
 22  Joined                    16654 non-null  object 
 23  Loaned From               1264 non-null   object 
 24  Contract Valid Until      17918 non-null  object 
 25  Height                    18159 non-null  object 
 26  Weight                    18159 non-null  object 
 27  LS                        16122 non-null  object 
 28  ST                        16122 non-null  object 
 29  RS                        16122 non-null  object 
 30  LW                        16122 non-null  object 
 31  LF                        16122 non-null  object 
 32  CF                        16122 non-null  object 
 33  RF                        16122 non-null  object 
 34  RW                        16122 non-null  object 
 35  LAM                       16122 non-null  object 
 36  CAM                       16122 non-null  object 
 37  RAM                       16122 non-null  object 
 38  LM                        16122 non-null  object 
 39  LCM                       16122 non-null  object 
 40  CM                        16122 non-null  object 
 41  RCM                       16122 non-null  object 
 42  RM                        16122 non-null  object 
 43  LWB                       16122 non-null  object 
 44  LDM                       16122 non-null  object 
 45  CDM                       16122 non-null  object 
 46  RDM                       16122 non-null  object 
 47  RWB                       16122 non-null  object 
 48  LB                        16122 non-null  object 
 49  LCB                       16122 non-null  object 
 50  CB                        16122 non-null  object 
 51  RCB                       16122 non-null  object 
 52  RB                        16122 non-null  object 
 53  Crossing                  18159 non-null  float64
 54  Finishing                 18159 non-null  float64
 55  HeadingAccuracy           18159 non-null  float64
 56  ShortPassing              18159 non-null  float64
 57  Volleys                   18159 non-null  float64
 58  Dribbling                 18159 non-null  float64
 59  Curve                     18159 non-null  float64
 60  FKAccuracy                18159 non-null  float64
 61  LongPassing               18159 non-null  float64
 62  BallControl               18159 non-null  float64
 63  Acceleration              18159 non-null  float64
 64  SprintSpeed               18159 non-null  float64
 65  Agility                   18159 non-null  float64
 66  Reactions                 18159 non-null  float64
 67  Balance                   18159 non-null  float64
 68  ShotPower                 18159 non-null  float64
 69  Jumping                   18159 non-null  float64
 70  Stamina                   18159 non-null  float64
 71  Strength                  18159 non-null  float64
 72  LongShots                 18159 non-null  float64
 73  Aggression                18159 non-null  float64
 74  Interceptions             18159 non-null  float64
 75  Positioning               18159 non-null  float64
 76  Vision                    18159 non-null  float64
 77  Penalties                 18159 non-null  float64
 78  Composure                 18159 non-null  float64
 79  Marking                   18159 non-null  float64
 80  StandingTackle            18159 non-null  float64
 81  SlidingTackle             18159 non-null  float64
 82  GKDiving                  18159 non-null  float64
 83  GKHandling                18159 non-null  float64
 84  GKKicking                 18159 non-null  float64
 85  GKPositioning             18159 non-null  float64
 86  GKReflexes                18159 non-null  float64
 87  Release Clause            16643 non-null  object 
dtypes: float64(38), int64(5), object(45)
memory usage: 12.4+ MB
In [8]:
fifa19['Body Type'].value_counts()
Out[8]:
Normal                 10595
Lean                    6417
Stocky                  1140
Messi                      1
C. Ronaldo                 1
Neymar                     1
Courtois                   1
PLAYER_BODY_TYPE_25        1
Shaqiri                    1
Akinfenwa                  1
Name: Body Type, dtype: int64
In [9]:
f, ax = plt.subplots(figsize=(8,6))
x = fifa19['Age']
ax = sns.distplot(x, bins=10)
plt.show()
In [10]:
f, ax = plt.subplots(figsize=(8,6))
x = fifa19['Age']
x = pd.Series(x, name="Age variable")
ax = sns.distplot(x, bins=10)
plt.show()
In [11]:
f, ax = plt.subplots(figsize=(8,6))
x = fifa19['Age']
ax = sns.distplot(x, bins=10, vertical = True)
plt.show()
In [12]:
f, ax = plt.subplots(figsize=(8,6))
x = fifa19['Age']
x = pd.Series(x, name="Age variable")
ax = sns.kdeplot(x)
plt.show()
In [13]:
f, ax = plt.subplots(figsize=(8,6))
x = fifa19['Age']
x = pd.Series(x, name="Age variable")
ax = sns.kdeplot(x, shade=True, color='r')
plt.show()
In [14]:
f, ax = plt.subplots(figsize=(8,6))
x = fifa19['Age']
ax = sns.distplot(x, kde=False, rug=True, bins=10)
plt.show()
In [15]:
f, ax = plt.subplots(figsize=(8,6))
x = fifa19['Age']
ax = sns.distplot(x, hist=False, rug=True, bins=10)
plt.show()
In [16]:
fifa19['Preferred Foot'].nunique()
Out[16]:
2
In [17]:
fifa19['Preferred Foot'].value_counts()
Out[17]:
Right    13948
Left      4211
Name: Preferred Foot, dtype: int64
In [18]:
f, ax = plt.subplots(figsize=(8, 6))
sns.countplot(x="Preferred Foot", data=fifa19, color="c")
plt.show()
In [19]:
f, ax = plt.subplots(figsize=(8, 6))
sns.countplot(x="Preferred Foot", hue="Real Face", data=fifa19)
plt.show()
In [20]:
f, ax = plt.subplots(figsize=(8, 6))
sns.countplot(y="Preferred Foot", data=fifa19, color="c")
plt.show()
In [21]:
g = sns.catplot(x="Preferred Foot", kind="count", palette="ch:.25", data=fifa19)
In [22]:
fifa19['International Reputation'].nunique()
Out[22]:
5
In [23]:
fifa19['International Reputation'].value_counts()
Out[23]:
1.0    16532
2.0     1261
3.0      309
4.0       51
5.0        6
Name: International Reputation, dtype: int64
In [24]:
f, ax = plt.subplots(figsize=(8, 6))
sns.stripplot(x="International Reputation", y="Potential", data=fifa19)
plt.show()
In [25]:
f, ax = plt.subplots(figsize=(8, 6))
sns.stripplot(x="International Reputation", y="Potential", data=fifa19, jitter=0.01)
plt.show()
In [26]:
f, ax = plt.subplots(figsize=(8, 6))
sns.stripplot(x="International Reputation", y="Potential", hue="Preferred Foot", 
                   data=fifa19, jitter=0.2, palette="Set2", dodge=True)
plt.show()
In [27]:
f, ax = plt.subplots(figsize=(8, 6))
sns.stripplot(x="International Reputation", y="Potential", hue="Preferred Foot", 
                   data=fifa19, palette="Set2", size=20, marker="D",
                   edgecolor="gray", alpha=.25)
plt.show()
In [28]:
f, ax = plt.subplots(figsize=(8, 6))
sns.boxplot(x=fifa19["Potential"])
plt.show()
In [29]:
f, ax = plt.subplots(figsize=(8, 6))
sns.boxplot(x="International Reputation", y="Potential", data=fifa19)
plt.show()
In [30]:
f, ax = plt.subplots(figsize=(8, 6))
sns.boxplot(x="International Reputation", y="Potential", hue="Preferred Foot", data=fifa19, palette="Set3")
plt.show()
In [31]:
f, ax = plt.subplots(figsize=(8, 6))
sns.violinplot(x=fifa19["Potential"])
plt.show()
In [32]:
f, ax = plt.subplots(figsize=(8, 6))
sns.violinplot(x="International Reputation", y="Potential", data=fifa19)
plt.show()
In [33]:
f, ax = plt.subplots(figsize=(8, 6))
sns.violinplot(x="International Reputation", y="Potential", hue="Preferred Foot", data=fifa19, palette="muted")
plt.show()
In [34]:
f, ax = plt.subplots(figsize=(8, 6))
sns.violinplot(x="International Reputation", y="Potential", hue="Preferred Foot", 
               data=fifa19, palette="muted", split=True)
plt.show()
In [35]:
f, ax = plt.subplots(figsize=(8, 6))
sns.pointplot(x="International Reputation", y="Potential", data=fifa19)
plt.show()
In [36]:
f, ax = plt.subplots(figsize=(8, 6))
sns.pointplot(x="International Reputation", y="Potential", hue="Preferred Foot", data=fifa19)
plt.show()
In [37]:
f, ax = plt.subplots(figsize=(8, 6))
sns.pointplot(x="International Reputation", y="Potential", hue="Preferred Foot", data=fifa19, dodge=True)
plt.show()
In [38]:
f, ax = plt.subplots(figsize=(8, 6))
sns.pointplot(x="International Reputation", y="Potential", hue="Preferred Foot", 
              data=fifa19, markers=["o", "x"], linestyles=["-", "--"])
plt.show()
In [39]:
f, ax = plt.subplots(figsize=(8, 6))
sns.barplot(x="International Reputation", y="Potential", data=fifa19)
plt.show()
In [40]:
f, ax = plt.subplots(figsize=(8, 6))
sns.barplot(x="International Reputation", y="Potential", hue="Preferred Foot", data=fifa19)
plt.show()
In [41]:
from numpy import median
f, ax = plt.subplots(figsize=(8, 6))
sns.barplot(x="International Reputation", y="Potential", data=fifa19, estimator=median)
plt.show()
In [42]:
f, ax = plt.subplots(figsize=(8, 6))
sns.barplot(x="International Reputation", y="Potential", data=fifa19, ci=68)
plt.show()
In [43]:
f, ax = plt.subplots(figsize=(8, 6))
sns.barplot(x="International Reputation", y="Potential", data=fifa19, ci="sd")
plt.show()
In [44]:
f, ax = plt.subplots(figsize=(8, 6))
sns.barplot(x="International Reputation", y="Potential", data=fifa19, capsize=0.2)
plt.show()
In [45]:
g = sns.relplot(x="Overall", y="Potential", data=fifa19)
In [46]:
f, ax = plt.subplots(figsize=(8, 6))
sns.scatterplot(x="Height", y="Weight", data=fifa19)
plt.show()
In [47]:
f, ax = plt.subplots(figsize=(8, 6))
ax = sns.lineplot(x="Stamina", y="Strength", data=fifa19)
plt.show()
In [48]:
f, ax = plt.subplots(figsize=(8, 6))
ax = sns.regplot(x="Overall", y="Potential", data=fifa19)
plt.show()
In [49]:
f, ax = plt.subplots(figsize=(8, 6))
ax = sns.regplot(x="Overall", y="Potential", data=fifa19, color= "g", marker="+")
plt.show()
In [50]:
f, ax = plt.subplots(figsize=(8, 6))
sns.regplot(x="International Reputation", y="Potential", data=fifa19, x_jitter=.01)
plt.show()
In [51]:
g= sns.lmplot(x="Overall", y="Potential", data=fifa19)
In [52]:
g= sns.lmplot(x="Overall", y="Potential", hue="Preferred Foot", data=fifa19)
In [53]:
g= sns.lmplot(x="Overall", y="Potential", hue="Preferred Foot", data=fifa19, palette="Set1")
In [54]:
g= sns.lmplot(x="Overall", y="Potential", col="Preferred Foot", data=fifa19)
In [55]:
g = sns.FacetGrid(fifa19, col="Preferred Foot")
In [56]:
g = sns.FacetGrid(fifa19, col="Preferred Foot")
g = g.map(plt.hist, "Potential")
In [57]:
g = sns.FacetGrid(fifa19, col="Preferred Foot")
g = g.map(plt.hist, "Potential", bins=10, color="r")
In [58]:
g = sns.FacetGrid(fifa19, col="Preferred Foot")
g = (g.map(plt.scatter, "Height", "Weight", edgecolor="w").add_legend())
In [59]:
g = sns.FacetGrid(fifa19, col="Preferred Foot", height=5, aspect=1)
g = g.map(plt.hist, "Potential")
In [60]:
fifa19_new = fifa19[['Age', 'Potential', 'Strength', 'Stamina', 'Preferred Foot']]
In [61]:
g = sns.PairGrid(fifa19_new)
g = g.map(plt.scatter)
In [62]:
g = sns.PairGrid(fifa19_new)
g = g.map_diag(plt.hist)
g = g.map_offdiag(plt.scatter)
In [63]:
g = sns.PairGrid(fifa19_new, hue="Preferred Foot")
g = g.map_diag(plt.hist)
g = g.map_offdiag(plt.scatter)
g = g.add_legend()
In [64]:
g = sns.PairGrid(fifa19_new, hue="Preferred Foot")
g = g.map_diag(plt.hist, histtype="step", linewidth=3)
g = g.map_offdiag(plt.scatter)
g = g.add_legend()
In [65]:
g = sns.PairGrid(fifa19_new, vars=['Age', 'Stamina'])
g = g.map(plt.scatter)
In [66]:
g = sns.PairGrid(fifa19_new)
g = g.map_upper(plt.scatter)
g = g.map_lower(sns.kdeplot, cmap="Blues_d")
g = g.map_diag(sns.kdeplot, lw=3, legend=False)
In [67]:
g = sns.JointGrid(x="Overall", y="Potential", data=fifa19)
g = g.plot(sns.regplot, sns.distplot)
In [68]:
import matplotlib.pyplot as plt
In [69]:
g = sns.JointGrid(x="Overall", y="Potential", data=fifa19)
g = g.plot_joint(plt.scatter, color=".5", edgecolor="white")
g = g.plot_marginals(sns.distplot, kde=False, color=".5")
In [70]:
g = sns.JointGrid(x="Overall", y="Potential", data=fifa19, space=0)
g = g.plot_joint(sns.kdeplot, cmap="Blues_d")
g = g.plot_marginals(sns.kdeplot, shade=True)
In [ ]:
In [71]:
g = sns.JointGrid(x="Overall", y="Potential", data=fifa19, height=5, ratio=2)
g = g.plot_joint(sns.kdeplot, cmap="Reds_d")
g = g.plot_marginals(sns.kdeplot, color="r", shade=True)
In [72]:
f, ax = plt.subplots(figsize=(8, 6))
ax = sns.regplot(x="Overall", y="Potential", data=fifa19);
In [73]:
sns.lmplot(x="Overall", y="Potential", col="Preferred Foot", data=fifa19, col_wrap=2, height=5, aspect=1)
Out[73]:
<seaborn.axisgrid.FacetGrid at 0x161dfa7dd50>
In [74]:
def sinplot(flip=1):
    x = np.linspace(0, 14, 100)
    for i in range(1, 7):
        plt.plot(x, np.sin(x + i * .5) * (7 - i) * flip)
In [75]:
sinplot()
In [76]:
sns.set()
sinplot()
In [77]:
sns.set_style("whitegrid")
sinplot()
In [78]:
sns.set_style("dark")
sinplot()
In [79]:
sns.set_style("white")
sinplot()
In [80]:
sns.set_style("ticks")
sinplot()
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]: